One of Canada’s largest retailers. The company offers merchandise including apparel, housewares, small appliances, electronics, hardware, grocery, as well as specialty services such as pharmacies, garden centers, and vision centers. The network consists of over 400 stores.

90 day Flow Plan

The company was challenged with moving goods efficiently while at the same time reacting to merchant asks. They needed to evaluate levers such as adjusting demands or adding another shift at the DC or accessing the temp labor pool or accessing flex transportation capacity.

Opportunity

With o9, the company was able to create a logistics forecast by taking the previous year data and applying ML algorithms that were enriched based on future events that the merchants had planned. Scenario planning

21 day Flow Plan

3 weeks out when real demand was available at the item-store level, the Integrated Planning Team were challenged in understanding if they were understaffed / over staffed and if they were enough dock doors and material handling capability.

Opportunity

With o9, a weekly plan is created driven off the current store demands and operates at an item / store / day granularity. This workflow drives tactical capacity planning changes before smoothing flow based on capacity limitations and flow prioritization defined by the merchant teams.

Day Planning

There was a need to plan every day for the next day, taking into account near term capacity problems. There were challenges in aligning capacity with demand and blocking flows of excess demand based on revised capacities and merchant priorities.

Opportunity

The day plan (executed once a day) is driven off the confirmed store order drop for execution and is at an item / store / day granularity. This workflow also drives next day capacity planning changes before blocking flow based on capacity limitations and flow prioritization defined by the merchant teams.

Key Functionalities Implemented

The o9 knowledge graph was used to build fully integrated E2E flow planning models and ML-based logistics forecasting. This allows for efficiently managing the volume the DC has to manage on a day-to-day basis. The plan drives alignment between capacity and demand, and smoothing of flow based on revised capacities and merchant priorities.

Systems Replaced

Excel and PowerPoint

Success Factors — 3 reasons why o9 was selected 

1. Optimal DC labor plans, outbound/inbound transportation plans, store receiving labor plans, and DC storage plans.
2. The ability to have one single connected system between forecasting and the fulfillment system.
3. Export outputs from o9 to drive downstream functions such as workforce planning.
4. Connect back to replenishment systems to re-prioritize transfer orders from DCs to stores.

KPI Impacted

1. Lower transportation costs.
2. Lower labor costs.
3. Lower out-of-stocks in store.